Machine-Learning-Based Uplink Throughput Prediction from Physical Layer Measurements

被引:10
|
作者
Eyceyurt, Engin [1 ]
Egi, Yunus [2 ,3 ]
Zec, Josko [4 ]
机构
[1] Nevsehir Haci Bektas Veli Univ, Fac Engn & Arts, Elect & Elect Engn, TR-50300 Nevsehir, Turkey
[2] Amer Univ Middle East, Coll Engn & Technol, Egaila 54200, Kuwait
[3] Sirnak Univ, Fac Engn, Elect & Elect Engn, TR-73000 Sirnak, Turkey
[4] Florida Inst Technol, Comp Engn & Sci, Melbourne, FL 32901 USA
关键词
machine learning; uplink throughput prediction; LTE & 5G radio metrics; PERFORMANCE;
D O I
10.3390/electronics11081227
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The uplink (UL) throughput prediction is indispensable for a sustainable and reliable cellular network due to the enormous amounts of mobile data used by interconnecting devices, cloud services, and social media. Therefore, network service providers implement highly complex mobile network systems with a large number of parameters and feature add-ons. In addition to the increased complexity, old-fashioned methods have become insufficient for network management, requiring an autonomous calibration to minimize utilization of the system parameter and the processing time. Many machine learning algorithms utilize the Long-Term Evolution (LTE) parameters for channel throughput prediction, mainly in favor of downlink (DL). However, these algorithms have not achieved the desired results because UL traffic prediction has become more critical due to the channel asymmetry in favor of DL throughput closing rapidly. The environment (urban, suburban, rural areas) affect should also be taken into account to improve the accuracy of the machine learning algorithm. Thus, in this research, we propose a machine learning-based UL data rate prediction solution by comparing several machine learning algorithms for three locations (Houston, Texas, Melbourne, Florida, and Batman, Turkey) and determine the best accuracy among all. We first performed an extensive LTE data collection in proposed locations and determined the LTE lower layer parameters correlated with UL throughput. The selected LTE parameters, which are highly correlated with UL throughput (RSRP, RSRQ, and SNR), are trained in five different learning algorithms for estimating UL data rates. The results show that decision tree and k-nearest neighbor algorithms outperform the other algorithms at throughput estimation. The prediction accuracy with the R2 determination coefficient of 92%, 85%, and 69% is obtained from Melbourne, Florida, Batman, Turkey, and Houston, Texas, respectively.
引用
收藏
页数:15
相关论文
共 50 条
  • [41] Machine-learning-based performance prediction of the energy pile heat pump system
    Chen, Yu
    Kong, Gangqiang
    Xu, Xiaoliang
    Hu, Shuaijun
    Yang, Qing
    JOURNAL OF BUILDING ENGINEERING, 2023, 77
  • [42] Improving fall prediction in Parkinson's disease: A machine-learning-based approach
    Panyakaew, P.
    Pornputtapong, N.
    Bhidayasiri, R.
    MOVEMENT DISORDERS, 2020, 35 : S306 - S307
  • [43] Machine-Learning-Based Prediction and Optimization of Mobile Metro-Core Networks
    Alvizu, Rodolfo
    Troia, Sebastian
    Maier, Guido
    Pattavina, Achille
    2018 IEEE PHOTONICS SOCIETY SUMMER TOPICAL MEETING SERIES (SUM), 2018, : 155 - 156
  • [44] Machine-learning-based cost prediction models for inpatients with mental disorders in China
    Ma, Yuxuan
    Tu, Xi
    Luo, Xiaodong
    Hu, Linlin
    Wang, Chen
    BMC PSYCHIATRY, 2025, 25 (01)
  • [45] Machine-Learning-Based User Position Prediction and Behavior Analysis for Location Services
    Jiang, Haiyang
    He, Mingshu
    Xi, Yuanyuan
    Zeng, Jianqiu
    INFORMATION, 2021, 12 (05)
  • [46] Machine-learning-based patient-specific prediction models for knee osteoarthritis
    Afshin Jamshidi
    Jean-Pierre Pelletier
    Johanne Martel-Pelletier
    Nature Reviews Rheumatology, 2019, 15 : 49 - 60
  • [47] Machine-Learning-Based Prediction of HVAC-Driven Load Flexibility in Warehouses
    Dadras Javan, Farzad
    Campodonico Avendano, Italo Aldo
    Najafi, Behzad
    Moazami, Amin
    Rinaldi, Fabio
    ENERGIES, 2023, 16 (14)
  • [48] Machine-Learning-Based Path Loss Prediction for In-Cabin Wireless Networks
    Moraitis, Nektarios
    Tsipi, Lefteris
    Vouyioukas, Demosthenes
    2024 IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING FOR COMMUNICATION AND NETWORKING, ICMLCN 2024, 2024, : 393 - 398
  • [49] Analysis and machine-learning-based prediction of beach accidents on a recreational beach in China
    Yuan Li
    Jialin Tang
    Chi Zhang
    Qinyi Li
    Shanhang Chi
    Yao Zhang
    Hongshuai Qi
    Chuang Zhang
    Anthropocene Coasts, 7 (1)
  • [50] Machine Learning and Deep Learning for Throughput Prediction
    Lee, Dongwon
    Lee, Joohyun
    12TH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN 2021), 2021, : 452 - 454